# The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability

arXiv: https://arxiv.org/abs/2404.02949 · HTML: https://mlsanity.com/paper/2404.02949/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 3 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Towards A Rigorous Science of Interpretable Machine Learning](https://mlsanity.com/paper/1702.08608/) (2017)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Adversarial Patch](https://mlsanity.com/paper/1712.09665/) (2017)
- [Interpreting CLIP's Image Representation via Text-Based Decomposition](https://mlsanity.com/paper/2310.05916/) (2023)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [Natural Language Descriptions of Deep Visual Features](https://mlsanity.com/paper/2201.11114/) (2022)
- [Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks](https://mlsanity.com/paper/2207.13243/) (2022)
- [Text-To-Concept (and Back) via Cross-Model Alignment](https://mlsanity.com/paper/2305.06386/) (2023)
- [Robust Feature-Level Adversaries are Interpretability Tools](https://mlsanity.com/paper/2110.03605/) (2021)
- [Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks](https://mlsanity.com/paper/2211.10024/) (2022)
- [Zoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Loss](https://mlsanity.com/paper/2401.11633/) (2024)
- [Prototype Generation: Robust Feature Visualisation for Data Independent Interpretability](https://mlsanity.com/paper/2309.17144/) (2023)

## Built on by (most cited first, 3 of 3)

- [Interpretability Can Be Actionable](https://mlsanity.com/paper/2605.11161/) (2026)
- [TracrBench: Generating Interpretability Testbeds with Large Language Models](https://mlsanity.com/paper/2409.13714/) (2024)
- [TextCAVs: Debugging vision models using text](https://mlsanity.com/paper/2408.08652/) (2024)

## Abstract (arXiv)

Interpretability techniques are valuable for helping humans understand and oversee AI systems. The SaTML 2024 CNN Interpretability Competition solicited novel methods for studying convolutional neural networks (CNNs) at the ImageNet scale. The objective of the competition was to help human crowd-workers identify trojans in CNNs. This report showcases the methods and results of four featured competition entries. It remains challenging to help humans reliably diagnose trojans via interpretability tools. However, the competition's entries have contributed new techniques and set a new record on the benchmark from Casper et al., 2023.